Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 451 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.4794. Min Act: -0.1700
Data Index: 4329862 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.2919. Min Act: -0.1700
Data Index: 1308023 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.2919. Min Act: -0.1700
Data Index: 2438353 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.2919. Min Act: -0.1700
Data Index: 4585997 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.2606. Min Act: -0.1700
Data Index: 2823429 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.1669. Min Act: -0.1700
Data Index: 8028462 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.1669. Min Act: -0.1700
Data Index: 508636 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.0731. Min Act: -0.1700
Data Index: 1830992 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.1356. Min Act: -0.1700
Data Index: 7174698 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.1044. Min Act: -0.1700
Data Index: 5250885 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.0419. Min Act: -0.1700
Data Index: 7503096 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.0106. Min Act: -0.1700
Data Index: 2236619 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.0106. Min Act: -0.1700
Data Index: 4099128 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4794. Min Range: -7.4794
Max Act: 7.0106. Min Act: -0.1700
Data Index: 7449385 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4794. Min Range: -7.4794
Max Act: 6.9481. Min Act: -0.1700
Data Index: 8491867 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4794. Min Range: -7.4794
Max Act: 6.9794. Min Act: -0.1700
Data Index: 2455363 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4794. Min Range: -7.4794
Max Act: 6.9794. Min Act: -0.1700
Data Index: 8781669 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4794. Min Range: -7.4794
Max Act: 6.9169. Min Act: -0.1700
Data Index: 848410 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4794. Min Range: -7.4794
Max Act: 6.9481. Min Act: -0.1700
Data Index: 483548 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4794. Min Range: -7.4794
Max Act: 6.9481. Min Act: -0.1700
Data Index: 201616 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #19